Code style adjustments

src/documents/management/commands/document_create_classifier.py

@@ -1,6 +1,4 @@
 import logging
-import os.path
-import pickle
 
 from django.core.management.base import BaseCommand
 from documents.classifier import DocumentClassifier
@@ -19,9 +17,7 @@ class Command(Renderable, BaseCommand):
 
     def handle(self, *args, **options):
         clf = DocumentClassifier()
-
         clf.train()
-
-        logging.getLogger(__name__).info("Saving models to " + settings.MODEL_FILE + "...")
-
+        logging.getLogger(__name__).info("Saving models to " +
+                                         settings.MODEL_FILE + "...")
         clf.save_classifier()

src/documents/management/commands/document_create_dataset.py

@@ -1,40 +0,0 @@
-from django.core.management.base import BaseCommand
-
-from documents.classifier import preprocess_content
-from documents.models import Document
-from ...mixins import Renderable
-
-
-class Command(Renderable, BaseCommand):
-
-    help = """
-        There is no help.
-    """.replace("    ", "")
-
-    def __init__(self, *args, **kwargs):
-        BaseCommand.__init__(self, *args, **kwargs)
-
-    def handle(self, *args, **options):
-        with open("dataset_tags.txt", "w") as f:
-            for doc in Document.objects.exclude(tags__is_inbox_tag=True):
-                labels = []
-                for tag in doc.tags.filter(automatic_classification=True):
-                    labels.append(tag.name)
-                f.write(",".join(labels))
-                f.write(";")
-                f.write(preprocess_content(doc.content))
-                f.write("\n")
-
-        with open("dataset_types.txt", "w") as f:
-            for doc in Document.objects.exclude(tags__is_inbox_tag=True):
-                f.write(doc.document_type.name if doc.document_type is not None and doc.document_type.automatic_classification else "-")
-                f.write(";")
-                f.write(preprocess_content(doc.content))
-                f.write("\n")
-
-        with open("dataset_correspondents.txt", "w") as f:
-            for doc in Document.objects.exclude(tags__is_inbox_tag=True):
-                f.write(doc.correspondent.name if doc.correspondent is not None and doc.correspondent.automatic_classification else "-")
-                f.write(";")
-                f.write(preprocess_content(doc.content))
-                f.write("\n")

src/documents/management/commands/document_retagger.py

@@ -11,7 +11,10 @@ from ...mixins import Renderable
 class Command(Renderable, BaseCommand):
 
     help = """
-        There is no help. #TODO
+        Using the current classification model, assigns correspondents, tags
+        and document types to all documents, effectively allowing you to
+        back-tag all previously indexed documents with metadata created (or
+        modified) after their initial import.
     """.replace("    ", "")
 
     def __init__(self, *args, **kwargs):
@@ -44,7 +47,7 @@ class Command(Renderable, BaseCommand):
 
         self.verbosity = options["verbosity"]
 
-        if options['inbox_only']:
+        if options["inbox_only"]:
             documents = Document.objects.filter(tags__is_inbox_tag=True).exclude(tags__is_archived_tag=True).distinct()
         else:
             documents = Document.objects.all().exclude(tags__is_archived_tag=True).distinct()
@@ -58,4 +61,4 @@ class Command(Renderable, BaseCommand):
 
         for document in documents:
             logging.getLogger(__name__).info("Processing document {}".format(document.title))
-            clf.classify_document(document, classify_document_type=options['type'], classify_tags=options['tags'], classify_correspondent=options['correspondent'], replace_tags=options['replace_tags'])
+            clf.classify_document(document, classify_document_type=options["type"], classify_tags=options["tags"], classify_correspondent=options["correspondent"], replace_tags=options["replace_tags"])